A1097
Title: Composite expectile estimation in partial functional linear regression model
Authors: Ping Yu - Shanxi Normal University (China) [presenting]
Abstract: Recent research and substantive studies have shown a growing interest in expectile regression (ER) procedures. Similar to quantile regression, ER concerning different expectile levels can provide a comprehensive picture of the conditional distribution of a response variable given predictors. Three composite-type ER estimators are proposed to improve estimation accuracy. The proposed ER estimators are the composite estimator, which minimizes the composite expectile objective function across expectiles; the weighted expectile average estimator, which takes the weighted average of expectile-specific estimators; and the weighted composite estimator, which minimizes the weighted composite expectile objective function across expectiles. Under certain regularity conditions, the convergence rate of the slope function is derived, the mean squared prediction error is obtained, and the asymptotic normality of the slope vector is established. Simulations are conducted to assess the empirical performance of various estimators. An application to the analysis of capital bike share data is presented. The numerical evidence endorses the theoretical results and confirms the superiority of the composite-type ER estimators to the conventional least squares and single ER estimators.
